Entropy-Based Breast Cancer Detection in Digital Mammograms Using World Cup Optimization Algorithm

Entropy-Based Breast Cancer Detection in Digital Mammograms Using World Cup Optimization Algorithm

Navid Razmjooy (Independent Researcher, Belgium), Vania V. Estrela (Universidade Federal Fluminense, Brazil) and Hermes Jose Loschi (State University of Campinas, Brazil)
Copyright: © 2020 |Pages: 18
DOI: 10.4018/IJSIR.2020070101

Abstract

Breast cancer is one of the deadliest cancers for women. Early detection of skin cancer gives a high chance for the women to escape from the malady and obtain a cure at the initial stages. In other words, early detection of breast cancer has a direct relation by the women's quality of life. In this case, mammography images are important. Indeed, the main test used for screening and early diagnosis of breast cancer is mammography. In recent years, computer-aided cancer detection has been turned into an active field of research and showed a promising future. In this study, a new optimization algorithm based on thresholding is introduced. A WCO algorithm is employed as the optimization algorithm. WCO is a new meta-heuristic approach which is inspired by the FIFA world cup challenge. The presented method utilizes random samples as candidate solutions from the search space inside the image histogram with considering to the objective function that is utilized by the Kapur's method.
Article Preview
Top

1. Introduction

Breast cancer is one of the most serious cancers of human life. It is the first reason of cancer death among women in the world; i.e. the most important reason for losing life in women is breast cancer (Broeders et al., 2018). In spite of extensive dissemination, timely diagnosis and treatment of this cancer are definitive and beneficial.

At present, mammography is the best diagnostic tool for breast cancer detection (Tabrizi, Vahdati, Khanahmadi, & Barjasteh, 2018). However, due to the type of breast tissue and also due to the use of x-rays with low density in the preparation of mammograms, the images have a low contrast (Sharifi, Jalilv, Elahimanesh, & Gharibi, 2018).

In addition, tumors have different sizes and shapes. Therefore, the diagnosis of lesions, especially in the early stages of the formation of work, is very difficult and tedious. Generally, according to statistics, early diagnosis of lesions has a dramatic effect on reducing cancer deaths.

In recent years, by the advancement of technology, especially in artificial intelligence, appropriate methods have been developed for this issue (Dolatkhah et al., 2018).

In the meantime, image processing techniques are developing as successful ways. Using methods and techniques for image processing and identifying patterns by automatic detection of cancer from images reduces human errors and increases the speed of detection.

In addition, the importance of the medical image processing, as it helps physicians and radiologists in facilitating the diagnosis of the disease, helps the patient to maintain the irreversible risks that will come about (Hay, Baser, Westerman, & Ford, 2018).

The expression of a suitable method for the segmentation of the cancerous images is the beginning of the work for the next stages of the diagnosis, such as feature extraction of the image which in turn will make it easy for the skin specialists to diagnose the disease (Ali, Vacavant, Grand-Brochier, Albouy-Kissi, & Boire, 2015; Alvarez & Iglesias, 2017; Bai, Li, Fu, Lv, & Zhang, 2017). In other words, the importance of the processing in medical images, including the processing of mammograms, helps physicians and radiologists to more easily detect the disease, thus protecting the patient from the irreparable risks that will come about (Gallego-Ortiz & Martel, 2019; Whitcomb et al., 2018).

Given the precise details of an exact segmentation for cancer, the method recommended should be carefully selected. The segmentation is to divide the image into non-identical areas. Areas are actually different objects in the image that are uniform in terms of texture or color.

The areas should not have small holes. The adjacent areas of a piece should have a significant difference with that area. Segmentation is used in cases such as image processing, machine vision, medical image processing, digital libraries, content-based information retrieval in pictures and videos, data transfer via the Internet, and image compression (Lambin et al., 2017).

Observation and diagnosis of breast cancer using non-invasive methods are based on inference method. Therefore, the accurate delineation of lesion and background by image processing makes it easier for physicians to diagnose breast cancer.

In the image processing applications, the diagnosis of cancer (such as breast cancer) can be considered as the first step in extracting the information needed for the next system (Bozorgtabar, Sedai, Roy, & Garnavi, 2017; Chatterjee, Dey, & Munshi, 2018; Codella et al., 2018; Dalila, Zohra, Reda, & Hocine, 2017; Hardie, Ali, De Silva, & Kebede, 2018; Kasmi & Mokrani, 2016; Kastl et al., 2017; Li & Shen, 2018; Rashid Sheykhahmad, Razmjooy, & Ramezani, 2015).

Recently, there are several research works which have performed on digital image processing based mammography, which are different in order to the masses detection in mammograms.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 12: 4 Issues (2021): Forthcoming, Available for Pre-Order
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing